问题描述
我想获得一些这样的信息。 一层的输入层和一层的输出层。
解决方法
您可以尝试总结,这是一个示例
from torchsummary import summary
vgg = models.vgg16()
summary(vgg,(3,224,224))
----------------------------------------------------------------
Layer (type) Output Shpae Param #
================================================================
Conv2d-1 [-1,64,224] 1792
ReLU-2 [-1,224] 0
Conv2d-3 [-1,224] 36928
ReLU-4 [-1,224] 0
MaxPool2d-5 [-1,112,112] 0
Conv2d-6 [-1,128,112] 73856
ReLU-7 [-1,112] 0
Conv2d-8 [-1,112] 147584
ReLU-9 [-1,112] 0
MaxPool2d-10 [-1,56,56] 0
Conv2d-11 [-1,256,56] 295168
ReLU-12 [-1,56] 0
Conv2d-13 [-1,56] 590080
ReLU-14 [-1,56] 0
Conv2d-15 [-1,56] 590080
ReLU-16 [-1,56] 0
MaxPool2d-17 [-1,28,28] 0
Conv2d-18 [-1,512,28] 1180160
ReLU-19 [-1,28] 0
Conv2d-20 [-1,28] 2359808
ReLU-21 [-1,28] 0
Conv2d-22 [-1,28] 2359808
ReLU-23 [-1,28] 0
MaxPool2d-24 [-1,14,14] 0
Conv2d-25 [-1,14] 2359808
ReLU-26 [-1,14] 0
Conv2d-27 [-1,14] 2359808
ReLU-28 [-1,14] 0
Conv2d-29 [-1,14] 2359808
ReLU-30 [-1,14] 0
MaxPool2d-31 [-1,7,7] 0
Linear-32 [-1,4096] 102764544
ReLU-33 [-1,4096] 0
Dropout-34 [-1,4096] 0
Linear-35 [-1,4096] 16781312
ReLU-36 [-1,4096] 0
Dropout-37 [-1,4096] 0
Linear-38 [-1,1000] 4097000
================================================================
Total params: 138357544
Trainable params: 138357544
Non-trainable params: 0
----------------------------------------------------------------